INDEX

Explanations

references to companies and their initiatives

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ngr

-0.14

.ca

-0.14

veis

-0.14

 proh

-0.14

 Sext

-0.14

 subsequ

-0.14

 solidarity

-0.14

esty

-0.14

vp

-0.14

 reluct

-0.14

POSITIVE LOGITS

cken

0.16

midt

0.15

 fert

0.15

 segment

0.15

oldt

0.14

æµ·å¤ĸ

0.14

adia

0.14

Ton

0.14

 Segment

0.14

Activations Density 0.038%

references to companies and their initiatives

No Comments

No Known Activations